Enables coding agents to run project-specific checks, replays, simulations, and queries as MCP tools, providing ground-truth feedback on config edits instead of guessing.
Enables building safe, programmable Code Mode MCP servers from upstream tool sources, with model-authored TypeScript running in a sandbox and tool calls routed to trusted host-side providers.
Enables MCP-capable clients to query the tool registry, check install status, get tool recommendations for CTF or bug-bounty work, and run installed security tools through a governed execution path.